{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.465150237083435, "min": 1.3654930591583252, "max": 3.295745611190796, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31412.8203125, "min": 23079.458984375, "max": 105463.859375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 75.0909090909091, "min": 41.94017094017094, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19824.0, "min": 14912.0, "max": 25392.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1692.9693457467758, "min": 1201.7416295213911, "max": 1722.5126695004046, "count": 4995 }, "SoccerTwos.Self-play.ELO.sum": { "value": 223471.9536385744, "min": 2406.796195441394, "max": 372426.6790666046, "count": 4995 }, "SoccerTwos.Step.mean": { "value": 49999960.0, "min": 9712.0, "max": 49999960.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999960.0, "min": 9712.0, "max": 49999960.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.030131956562399864, "min": -0.15228120982646942, "max": 0.1894119828939438, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.007550239562988, "min": -28.476587295532227, "max": 30.87415313720703, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.030558589845895767, "min": -0.15508036315441132, "max": 0.19559666514396667, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.0642924308776855, "min": -29.00002670288086, "max": 31.88225555419922, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.010691727014412558, "min": -0.5333333333333333, "max": 0.4856428567852293, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.4219996929168701, "min": -68.67199993133545, "max": 57.80520033836365, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.010691727014412558, "min": -0.5333333333333333, "max": 0.4856428567852293, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.4219996929168701, "min": -68.67199993133545, "max": 57.80520033836365, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017341579508502035, "min": 0.009301236225292086, "max": 0.025968072371324525, "count": 2426 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017341579508502035, "min": 0.009301236225292086, "max": 0.025968072371324525, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09059043924013774, "min": 0.00011423783798818477, "max": 0.125458358724912, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09059043924013774, "min": 0.00011423783798818477, "max": 0.125458358724912, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09162350594997407, "min": 0.00011680398868823735, "max": 0.12798677186171215, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09162350594997407, "min": 0.00011680398868823735, "max": 0.12798677186171215, "count": 2426 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725550746", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\user\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1725696450" }, "total": 145702.31955729995, "count": 1, "self": 0.21180839993758127, "children": { "run_training.setup": { "total": 0.04927489999681711, "count": 1, "self": 0.04927489999681711 }, "TrainerController.start_learning": { "total": 145702.05847400002, "count": 1, "self": 63.13300721294945, "children": { "TrainerController._reset_env": { "total": 5.890054500836413, "count": 250, "self": 5.890054500836413 }, "TrainerController.advance": { "total": 145632.91117428633, "count": 3441532, "self": 61.21651998948073, "children": { "env_step": { "total": 41668.09676003369, "count": 3441532, "self": 30362.51483185694, "children": { "SubprocessEnvManager._take_step": { "total": 11268.861821938248, "count": 3441532, "self": 365.7036327709793, "children": { "TorchPolicy.evaluate": { "total": 10903.158189167269, "count": 6277388, "self": 10903.158189167269 } } }, "workers": { "total": 36.720106238499284, "count": 3441532, "self": 0.0, "children": { "worker_root": { "total": 145614.52784918074, "count": 3441532, "is_parallel": true, "self": 122174.26004388125, "children": { "steps_from_proto": { "total": 0.26578550069825724, "count": 500, "is_parallel": true, "self": 0.05441710044397041, "children": { "_process_rank_one_or_two_observation": { "total": 0.21136840025428683, "count": 2000, "is_parallel": true, "self": 0.21136840025428683 } } }, "UnityEnvironment.step": { "total": 23440.00201979879, "count": 3441532, "is_parallel": true, "self": 1307.0701382493135, "children": { "UnityEnvironment._generate_step_input": { "total": 1101.489669339615, "count": 3441532, "is_parallel": true, "self": 1101.489669339615 }, "communicator.exchange": { "total": 16845.99803419324, "count": 3441532, "is_parallel": true, "self": 16845.99803419324 }, "steps_from_proto": { "total": 4185.4441780166235, "count": 6883064, "is_parallel": true, "self": 903.6154094468802, "children": { "_process_rank_one_or_two_observation": { "total": 3281.8287685697433, "count": 27532256, "is_parallel": true, "self": 3281.8287685697433 } } } } } } } } } } }, "trainer_advance": { "total": 103903.59789426316, "count": 3441532, "self": 463.95441531349206, "children": { "process_trajectory": { "total": 12809.12674184877, "count": 3441532, "self": 12799.70952404855, "children": { "RLTrainer._checkpoint": { "total": 9.417217800219078, "count": 100, "self": 9.417217800219078 } } }, "_update_policy": { "total": 90630.5167371009, "count": 2426, "self": 5748.6619745066855, "children": { "TorchPOCAOptimizer.update": { "total": 84881.85476259422, "count": 72780, "self": 84881.85476259422 } } } } } } }, "trainer_threads": { "total": 1.00000761449337e-06, "count": 1, "self": 1.00000761449337e-06 }, "TrainerController._save_models": { "total": 0.12423699989449233, "count": 1, "self": 0.0025555999018251896, "children": { "RLTrainer._checkpoint": { "total": 0.12168139999266714, "count": 1, "self": 0.12168139999266714 } } } } } } }